We are here to help. Contact us.

Knowledge-Based Systems

In today’s computing and networking environment, system complexity has grown to the point where it can no longer be handled manually by human experts. There is a pressing need for automation which takes the system environment into consideration to determine appropriate actions. In response, our ACS researchers are developing cutting edge technologies that meet at the intersection of big data analytics, wireless networking, and cyber security.

Key to our technology development efforts is our world-class research in new machine learning paradigms. We are creating advanced machine learning capabilities on the DARPA PPAML (Probabilistic Programming for Advanced Machine Learning) and related programs, and applying them to an array of problems in networking, cyber security, sensor fusion, autonomy, and healthcare analytics.

Our deep expertise and familiarity with military networks, modeling and simulation, and virtualization technologies were instrumental to our selection by the U.S. Army Research Laboratory for a five-year program where we will be developing innovative cyber experimentation techniques and working with a team of five universities to help them validate their basic research in the science of cyber security. At the center of this program is our CyberVAN product, which supports a hybrid emulation environment for cyber experimentation with hosts running software applications that exchange data over simulated wireless and wired networks using simulators like ns-2, ns-3, OPNET, and QualNet.

We are applying our analytics and wireless networking expertise to the DARPA Wireless Network Defense program, where we are developing techniques to detect and mitigate attacks against wireless control plane protocols. Another exciting and growing area of research is collaborative autonomy, including our work on DARPA programs DBM (Distributed Battle Management) and CODE (Collaborative Operation in Denied Environments). In these programs we are developing capabilities for distributed situation understanding, multi-modal sensor fusion, and reliable information distribution in a contested environment. On the DARPA CFAR (Cyber Fault-Tolerant Attack Recovery) program, we are developing a cyber fault-tolerant runtime environment that provides performance guarantees and attack recovery for vulnerable applications via the principled use and support of heterogeneous variants.

More broadly, our researchers are applying our big data advanced analytics capabilities to healthcare, to help find undiagnosed patients with rare diseases by creating models of the patient journey using insurance claims data.